CDS PhD Student Aram-Alexandre Pooladian and Assistant Professor Jonathan Niles-Weed Win Best Paper Award at NeurIPS’ OTML Workshop

CDS PhD student Aram-Alexandre Pooladian and CDS Assistant Professor Jonathan Niles-Weed recently won the Best Paper Award at the Virtual OTML Workshop at NeurIPS 2021 (OTML stands for Optimal Transport and Machine Learning). The OTML Workshop series has been pivotal in developing optimal transport research in recent years. NeurIPS is an interdisciplinary annual conference focused on machine learning and includes a series of presentations and workshops.

The team’s award-winning paper, “Entropic estimation of optimal transport maps”, presents a computationally tractable approach for estimating the optimal map between two distributions over ℝd by leveraging an entropic version of Brenier’s theorem. Ultimately, they demonstrate that their proposed estimator is easy to compute using Sinkhorn’s algorithm. In comparison to other current methods, which are slow to evaluate when the number of samples is large, their estimator is scalable even for massive data sets and with a much lower computational cost.

“Needless to say, I’m pretty happy with how this paper turned out! We’re surprised at how well our method works, given its relative simplicity. Figuring out how to prove the results we wanted took us a while, but now it’s opening up new research avenues, which is great,” says Aram-Alexandre.

Aram-Alexandre Pooladian is a second-year PhD student at CDS, advised by Jonathan Niles-Weed. His research interests are at the intersection of optimization theory, high-dimensional statistics, and optimal transport.

Jonathan Niles-Weed is Assistant Professor of Mathematics and Data Science at CDS. His research interests surround statistics, probability, and the mathematics of data science. He is particularly interested in statistical and computational problems arising from data with geometric structure. His recent work focuses specifically on optimal transport.

By Ashley C. McDonald




Official account of the Center for Data Science at NYU, home of the Undergraduate, Master’s, and Ph.D. programs in Data Science.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Dstl Satellite Imagery Feature Detection using Segnet and Canet

Predicting the Risk of Cervical Cancer Using Gradient Boosted Decision Trees

9 Techniques to Write Your Code Efficiently

Scikit-Learn for Text Analysis of Amazon Fine Food Reviews

What is CPA model?

Topic Modeling and Latent Dirichlet Allocation (LDA) in Python

My Interview Experience at ZS

South East Asia (ASEAN) Trade 2011–2020

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
NYU Center for Data Science

NYU Center for Data Science

Official account of the Center for Data Science at NYU, home of the Undergraduate, Master’s, and Ph.D. programs in Data Science.

More from Medium

A Quick Glance at Machine Learning in Data Science:

Bussiness utility of uncertain machine learning classiffiers

Fatal mistakes to avoid when designing an AI system

Hypergraphs Applications in Machine Learning